AI-900 Practice Question: Describe features of generative AI workloads on Azure
What is 'Azure AI Search' (formerly Cognitive Search) and how does it support generative AI?
⚠ Common exam trap
Many candidates confuse Azure AI Search with a general-purpose web crawler or a simple SQL full-text search plugin, overlooking its key role as a dedicated retrieval engine for RAG in generative AI workloads.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
A search service that retrieves relevant document chunks for RAG — grounding LLM responses in source material
Azure AI Search is a cloud search service that indexes and retrieves relevant document chunks, which can be used in a Retrieval-Augmented Generation (RAG) pattern. By providing grounded, source-specific context to a large language model (LLM), it helps ensure the generated responses are based on factual, retrieved data rather than solely on the model's training data.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A web crawling service that indexes publicly available web content for Azure customers
Why it's wrong here
This option describes a web crawler like a search engine spider, which indexes publicly reachable pages across the internet. Azure AI Search is not a web-crawling service; it is designed to import and index your own organization's private data from sources such as Azure Blob Storage, Cosmos DB, SQL databases, and SharePoint. Using indexers, it can connect to those sources, enrich content with AI skills, and then expose a search endpoint over that contained dataset. Public web indexing belongs to a different tool, such as Bing's crawler.
- ✓
A search service that retrieves relevant document chunks for RAG — grounding LLM responses in source material
Why this is correct
This option correctly describes Azure AI Search's role as the retrieval engine in a Retrieval-Augmented Generation (RAG) solution. In practice, documents are chunked, embedded into vectors, and stored in an Azure AI Search index; at query time, the service performs hybrid retrieval (keyword, semantic, and vector) to return the most relevant chunks. Those chunks are then inserted into an LLM's prompt as grounding context, enabling the model to cite real source material and reduce hallucination. This is precisely the recommended architecture for grounding Azure OpenAI models on private, domain-specific data.
- ✗
A service that searches Azure resource configurations for compliance violations
Why it's wrong here
This option describes Azure Policy, an Azure governance service that evaluates resource configurations against compliance rules such as allowed locations or required tags. Azure Policy never indexes content or retrieves document chunks; it only audits and enforces control-plane state. Azure AI Search, by contrast, is a data-plane PaaS service that ingests documents and vectors, builds searchable indexes, and returns ranked matches for RAG and enterprise search. The confusion conflates operational compliance assessment with cognitive search over unstructured content.
- ✗
A full-text search plugin that adds search to Azure SQL databases
Why it's wrong here
This option describes SQL Server full-text search, a built-in feature of Azure SQL Database and SQL Managed Instance that enables basic keyword-based searching over character columns. It is a plugin-like capability inside the database engine, not a standalone cloud service. Azure AI Search is a fully managed external service that can use Azure SQL as a data source via an indexer, but it adds semantic ranking, vector search, and AI enrichment that SQL full-text search cannot provide. The confusion conflates a database engine feature with a separate search service designed for RAG pipelines.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
Key term
Generative AI
Generative AI is a type of artificial intelligence that creates new content—like text, images, or code—by learning patterns from existing data.
About these practice questions
One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.